Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    questions and expressions related to personal identity and perception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Knox
    -0.17
    pas
    -0.16
    anche
    -0.15
     Roll
    -0.15
    .roll
    -0.15
    ph
    -0.15
    ros
    -0.14
    .dtd
    -0.14
     Tanks
    -0.14
     thing
    -0.14
    POSITIVE LOGITS
    chez
    0.16
    antal
    0.15
    wav
    0.15
    ometr
    0.15
    alam
    0.15
    éı¡
    0.14
     *(*
    0.14
    iffies
    0.14
    adora
    0.14
    atsapp
    0.14
    Act Density 0.001%

    No Known Activations